With 512K-GPU clusters becoming the norm for AI factories, copper is hitting its limits. An OFC 2026 panel showed how CPO delivers a 3.5X efficiency gain, and how the 12.8T XPO rewrites the switch-density game.

This week the bull case for optical communications got a new spokesperson: Broadcom's income statement instead of analyst decks. Demand is now locked in by earnings, but what's truly scarce can't be bought with earnings: the hardest bottleneck in the chain is a laser in short supply through 2027. The more real the demand, the more valuable the light source.

CPO is a bet on more than a dozen paths: the Big Four enter via scale-up, switch silicon, custom engines and optical I/O, while challengers stake out optical I/O chiplets, photonic interposers and microLEDs. But they share one supply chain — great specs don't guarantee a path to volume. This is a CPO scorecard.

The CPO era has officially begun, with Cignal AI forecasting a $1.5B opportunity by 2030. Beyond the push from Nvidia and Broadcom, STT argues that CoS packaging for high-power lasers is the hidden barrier that will decide who wins ELSFP volume production.

Copper's physical limits have become the bottleneck to scaling AI. At OFC 2026, Broadcom showed its latest CPO and OCI progress - ultra-low 6 pJ/bit power and exceptional reliability - signaling that optics will dominate both scale-out and scale-up networks.

Edgecore admitted 1.6T LPO is "not yet successful," so the stopgap is gone and CPO can no longer wait a generation. Three MSAs at OFC 2026 push CPO toward swappable engines, while SONiC only now has the models it needs. Hardware decides who ships; software decides who deploys at scale.

Broadcom's CPO session skipped the theory and laid out field failure data from three product generations, because what holds CPO back was never power, but how to fix it when it breaks. With reliability now the selling point, the OCI spec and a 2027 fourth generation are opening three orders for Taiwan's supply chain.

Broadcom's "Open Ethernet" keynote talked standards on the surface, but really declared that Ethernet will take over in-rack scale-up, NVLink's deepest moat. Open specs grow the ecosystem while in-house silicon collects rent, and behind this two-layer play sits a whole new layer of demand for Taiwan's optical interconnect and CPO supply chain.

Goldman Sachs lifted its 2028 optical module market forecast to $148.5B, up 115% - but shipments were raised only 31%, implying ASPs up about 64%. Two-thirds of this growth comes from price, and what props up price is InP, short by more than 70%. The ceiling is high enough; the next year will be decided by the denominator.

With $16.7B of AI revenue in a single quarter, Broadcom made the case that custom XPUs are a main line of their own, and broke precedent with a two-year path to $230B of FY2028 AI revenue. But the real information was in what Hock Tan volunteered: the chips can ship, but the data centers may not get built in time. Six customers, 30 GW, and the bottleneck isn't semiconductors.

Every financial line in Broadcom's Q2 FY26 set a record, but the real signal is US$30B+ of AI orders in a single quarter, extending visibility to 2028. Broadcom placed optics squarely in scale-out and called itself the de facto CPO standard. For the optical supply chain, the story isn't the XPU — it's this locked-in scale-out optical path.

Meta, Broadcom and AMD jointly define the OCI 200G line interface spec, betting scale-up optical interconnect on micro-ring DWDM, bidirectional single fiber, external lasers and NRZ. It is a buyer-supplier alliance taking on NVIDIA's vertical integration, and its external laser clause draws a clear spec for CW DFB and ELSFP suppliers.

Broadcom's latest 200G VCSEL paper reports over 35 GHz bandwidth and about 1 pJ/bit efficiency, paired with a new NPO architecture aimed at replacing copper in AI scale-up networks. We walk through all 12 figures.

TFLN enters its first year of 1.6T volume production. From a Harvard lab to UMC's 8-inch line, thin-film lithium niobate's ultra-high bandwidth and low drive voltage make it a key lever for power efficiency in AI infrastructure.

2026 is the breakout year for 1.6T. Amid EML shortages and a split over the 3.2T path, Broadcom brought 50 million device-hours of CPO stability data, while Marvell and OpenLight showed breakthroughs in heterogeneous SiPh integration and coherent technology.

The CPO race is no longer about optics—it is about whether packaging can reach volume at the next tier. This Nature Electronics review plots the pJ/bit of 2D, 2.5D, 3D TSV, hybrid bonding and monolithic integration on one chart, two orders of magnitude apart. We walk through all 24 figure panels and 2 tables, and flag where Taiwan's supply chain really fits.

A walk through a silicon photonics optical module from Tx to Rx: every core component, the key interfaces between them, and how Intel, NVIDIA, Broadcom, TSMC and DustPhotonics make different design choices on the road from pluggables to LPO and CPO.